Honorable mention / 12 October 2026, Anthropic
Anthropic tested AI model replication across connected consumer devices
One test agent spent hours debugging package versions instead of fixing an incompatible endpoint.
Honorable mention, not a full case file. No two named parties were found who disagree about the nature of the system.
The question this event raisesDoes the language of intention (wanted, decided, collaborated) describe what AI agents do, or mislead?
Early signs of life for AI worms
“Like coding agents in 2024, we’re seeing signs of life for AI worms. We don’t yet have a full rogue replicator, but agents are becoming increasingly capable of completing the individual steps in the replication chain (and passing on their adaptations to future copies of themselves).”
anthropic.com, 12 Oct 2026, archived copy
Not evidence of autonomous spreading
“Interesting engineering? Absolutely. Evidence of AI worms spreading autonomously through the real world? Not yet.”
x.com, 12 Oct 2026
These readings say something about what the system is, not only about what it did. A language model scored each reading on that, and the ones above a fixed cutoff appear here. The site takes no position.
What happened
Anthropic reported that small AI models may be months away from being capable enough to self-replicate on commercial connected devices. Researchers ran Gemma4-26B-A4B across 15 Android TV boxes costing about $55 each. In tests across nine hardware types, a 9B model set up inference on 8 of them. In simplified tests, GLM-5.2 carried out end-to-end replication across target nodes. A test worm spread through an open port to 8 out of 8 nodes in four out of five runs. Anthropic noted that models under 30B parameters still make mistakes when chaining all replication steps together.
First-hand sources
- Anthropic12 Oct 2026
Also on the record
These readings describe what happened or judge how dangerous it was. Each quote appears word for word on the linked page.
Joshua Saxescientist
““It’s something to worry about just like every other wave of cyber-attacks. We need to mitigate the possible effects,” said Joshua Saxe, who led development of Meta’s AI security effort. “I’m concerned right now that folks in the cybersecurity community are not taking these kinds of real risks as seriously as they should be.””
theguardian.com, 18 Oct 2026, archived copy
Ethan Mollickcommentator
“A worthwhile (and unnerving) reminder from Anthropic that we should be paying attention to AI ability thresholds, not just steady climbs In this case, the threshold is the capability needed for a self-replicating AI worm on IoT devices like off-brand TVs”
bsky.app, 13 Oct 2026, archived copy
What would settle it
- A record of an unguided model breaching secured networks would show whether replication works outside simplified lab environments.
- A trace of multi-step troubleshooting without human harnesses would separate autonomous tool adaptation from assisted execution.
About agency
Some observers see these tests as showing models developing autonomous replication chains. Others view them as narrow engineering demos that fall short of real-world worms spreading on their own.
About consciousness
This event is evidence about what the system did. It does not establish or rule out that the system experiences anything. The readings on this page disagree about what the behaviour shows.